Dynamic Fatigue Assessment of Additively Manufactured Ti-6Al-4V Using Hybrid Acoustic Emission and Digital Image Correlation with Bayesian Machine Learning Calibration

**Abstract:** This paper introduces a novel, accelerated fatigue testing protocol for additively manufactured (AM) Ti-6Al-4V, combining real-time Acoustic Emission (AE) monitoring with Digital Image Correlation (DIC) crack length measurement and Bayesian machine learning calibration to predict fatigue life. The framework dynamically adjusts loading based on structural integrity assessment, offering significant time savings compared to traditional S-N curve methodologies. The incorporation of Bayesian techniques allows for robust life prediction even with limited data, crucial for optimizing AM component design and reducing production costs. The proposed methodology offers a demonstrably robust and efficient means for fatigue characterization, with immediate applicability to Aerospace, Medical, and Automotive industries.